A computer-implemented method according to one embodiment includes receiving, at a scheduler, a training data instance and a target instance, generating, by the scheduler, an input sequence from the training data instance and the target instance, sending the input sequence from the scheduler to an encoder, mapping, by the encoder, the input sequence to a feature vector, sending the feature vector from the encoder to the scheduler, sending the feature vector from the scheduler to a predictor, and mapping, by the predictor, the feature vector to a class vector to create a label for the target instance.
Legal claims defining the scope of protection, as filed with the USPTO.
3. The computer-implemented method of claim 1, wherein the training data instance includes a sentence represented as a dependency tree.
4. The computer-implemented method of claim 1, wherein the training data instance includes a plurality of identified and labeled dependencies.
5. The computer-implemented method of claim 1, wherein the target instance includes a portion of a dependency tree.
6. The computer-implemented method of claim 1, wherein the target instance includes a subtree within a dependency tree.
7. The computer-implemented method of claim 1, wherein the feature vector includes one or more features of the target instance within the training data instance.
8. The computer-implemented method of claim 1, wherein the scheduler is selected from a group consisting of a logistic regression module, a support vector machine (SVM), and a fully connected neural network.
9. The computer-implemented method of claim 1, wherein the encoder is selected from a group consisting of a recurrent neural network (RNN), a hidden Markov model, and long-short term memory.
10. The computer-implemented method of claim 1, wherein the predictor is selected from a group consisting of a logistic regression module, a support vector machine (SVM), and a fully connected neural network.
11. The computer-implemented method of claim 1, wherein the feature vector is sent to the predictor in response to the scheduler determining that the feature vector is sufficient to invoke the predictor, wherein the feature vector is not sent to the predictor in response to the scheduler determining that the feature vector is not sufficient to invoke the predictor.
12. The computer-implemented method of claim 1, wherein an input sequence is generated from the training data instance and the target instance based on a predetermined strategy, wherein the predetermined strategy includes the cold-start strategy where the scheduler adopts a uniform distribution to generate the input sequence.
13. The computer-implemented method of claim 1, wherein an input sequence is generated based on a predetermined strategy, wherein the predetermined strategy includes a warmup strategy, where the scheduler adopts the epsilon-greedy method to generate the input sequence.
14. The computer-implemented method of claim 1, wherein an input sequence is generated based on a predetermined strategy, wherein the predetermined strategy includes the heat-converge strategy where the scheduler adopts the maximum-likelihood action to generate the input sequence.
16. The computer program product of claim 15, wherein the training data instance includes a sentence represented as a dependency tree.
19. The system of claim 18, wherein the feature vector is sent by the scheduler to the predictor in response to the scheduler determining that the feature vector is sufficient to invoke the predictor, wherein the feature vector is not sent to the predictor in response to the scheduler determining that the feature vector is not sufficient to invoke the predictor.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
June 13, 2019
October 1, 2024
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.